Generalized advantage estimation combined with trust region optimization enables stable neural network policy learning for complex continuous control from raw kinematics.
hub Mixed citations
Trust Region Policy Optimization
Mixed citation behavior. Most common role is background (60%).
23
Pith papers citing it
Background
60% of classified citations
abstract
We describe an iterative procedure for optimizing policies, with guaranteed monotonic improvement. By making several approximations to the theoretically-justified procedure, we develop a practical algorithm, called Trust Region Policy Optimization (TRPO). This algorithm is similar to natural policy gradient methods and is effective for optimizing large nonlinear policies such as neural networks. Our experiments demonstrate its robust performance on a wide variety of tasks: learning simulated robotic swimming, hopping, and walking gaits; and playing Atari games using images of the screen as input. Despite its approximations that deviate from the theory, TRPO tends to give monotonic improvement, with little tuning of hyperparameters.
hub tools
citation-role summary
background 3
extension 1
method 1
citation-polarity summary
representative citing papers
EFE-based planning is formulated as variational free energy minimization with epistemic priors, decomposing into expected plan costs plus a complexity term.
EFE-based active inference planning is characterized as VFE on an augmented model plus entropy and planning corrections, with a derived message-passing implementation and grid-world validation.
Information geometry constrains intrinsic rewards to strictly concave functions of reciprocal occupancy, with geodesic interpolation on the occupancy manifold yielding a scalar-parameter family that includes count-based and max-entropy exploration.
Temporal Transfer Learning selects source tasks for zero-shot transfer of RL policies to solve a range of coarse-grained advisory autonomy hold durations in traffic optimization more reliably than baselines.
The paper establishes the first tilde O(epsilon^{-1}) upper bounds and matching lower bounds for forward-KL-regularized offline contextual bandits under single-policy concentrability in both tabular and general function approximation settings.
SmoothCruiser achieves O~(1/epsilon^4) problem-independent sample complexity for value estimation in entropy-regularized MDPs and games via a generative model.
Advantage-guided diffusion (SAG and EAG) steers sampling in diffusion world models to higher-advantage trajectories, enabling policy improvement and better sample efficiency on MuJoCo tasks.
A hybrid neural policy operating in impulse space enables physics-based characters to track exaggerated, dynamically infeasible motions that standard DRL methods cannot stabilize.
DDPG is a model-free actor-critic algorithm that learns continuous control policies end-to-end from states or pixels using deterministic policy gradients and deep networks, solving more than 20 physics tasks competitively with full-information planning methods.
Dynamic Gradient Gating monitors lm_head gradient norms to safely reuse rollout batches in RLVR, achieving up to 2.93x sample efficiency and 2.14x wall-clock speedup across math, ALFWorld, WebShop, and QA tasks.
Reinforcement learning with semantic rewards lets LLMs gain low-resource language skills without the alignment tax that degrades general capabilities in supervised fine-tuning.
A method trains discrete diffusion policies for combinatorial RL by matching to a PMD-regularized target distribution, reporting SOTA performance and sample efficiency on DNA generation, macro-action, and multi-agent benchmarks.
Shows entropy coupling limits DSAC on discrete tasks and introduces a generalized actor-critic framework with m-step critics and novel entropy-regularized objectives that perform robustly on Atari.
YANN-RL initializes RL actor and critic networks with explicit multi-parametric linear MPC solutions via YANNs to start from linear optimal control performance and then learn nonlinear policies through online interaction.
Introduces polychromic objectives adapted into PPO via vine sampling and modified advantages, showing higher success rates and better coverage under perturbations on BabyAI, Minigrid, and algorithmic tasks.
A Goal-Conditioned Decision Transformer is adapted for offline multi-goal RL and shown to outperform online baselines on a new Franka Emika Panda dataset.
Introduces α-fair HATRPO and HAPPO algorithms that integrate α-fairness into HATRL via a weighted advantage function while claiming to preserve convergence to Nash equilibria.
OmniVLA-RL uses a mix-of-transformers architecture and flow-matching reformulated as SDE with group segmented policy optimization to surpass prior VLA models on LIBERO benchmarks.
TriCoD is a cooperative decision-making framework using twin-world deduction and adaptive switching between DRL and model-driven methods to enable safe, dynamic AV platooning in hybrid traffic.
Reinforcement learning is advanced for communication-efficient federated optimization and for preference-aligned, contextually safe policies in large language models.
A survey provides a task-based formalization of meta-learning and meta-RL while chronicling algorithms that lead to DeepMind's Adaptive Agent.
citing papers explorer
-
Reinforcement Learning for Scalable and Trustworthy Intelligent Systems
Reinforcement learning is advanced for communication-efficient federated optimization and for preference-aligned, contextually safe policies in large language models.